Applications of support vector machines to cancer classification with microarray data

@article{Chu2005ApplicationsOS,
  title={Applications of support vector machines to cancer classification with microarray data},
  author={Feng Chu and Lipo Wang},
  journal={International journal of neural systems},
  year={2005},
  volume={15 6},
  pages={
          475-84
        }
}
  • Feng Chu, Lipo Wang
  • Published 1 December 2005
  • Computer Science
  • International journal of neural systems
Microarray gene expression data usually have a large number of dimensions, e.g., over ten thousand genes, and a small number of samples, e.g., a few tens of patients. [] Key Method Dimensionality reduction methods, such as principal components analysis (PCA), class-separability measure, Fisher ratio, and t-test, are used for gene selection. A voting scheme is then employed to do multi-group classification by k(k - 1) binary SVMs. We are able to obtain the same classification accuracy but with much fewer…
View on PubMed
www3.ntu.edu.sg
186 Citations
Highly Influential Citations
8
Background Citations
45
Methods Citations
57
Results Citations
1

186 Citations

Citation Type

Citation Type

A Multiclass Classification of Cancer Data: Using a Kernel Based Clustering k-NN Support
TLDR
A multiclass classification has been applied to cancer data, represented by SRBCT data set, in a pair wise manner.
Pattern Analysis in DNA Microarray Data through PCA-Based Gene Selection
TLDR
This paper proposes a new methodology that is based on the application of Principal Component Analysis and other statistical tools to gain insight in the identification of relevant genes and shows that it is possible to reduce considerably the number of genes while increasing the performance of well known classifiers.
Cancer Classification in Microarray Data using a Hybrid Selective Independent Component Analysis and υ-Support Vector Machine Algorithm
TLDR
This paper uses selective independent component analysis (SICA) for decreasing the dimension of microarray data and shows that the proposed algorithm has higher accuracy and validity in order to increase the classification accuracy.
Improving pattern classification of DNA microarray data by using PCA and logistic regression
TLDR
A new methodology based on Principal Component Analysis and Logistics Regression is proposed that enables the selection of particular genes that are relevant for classification in DNA microarrays.
Learning Microarray Cancer Datasets by Random Forests and Support Vector Machines
  • Myungsook Klassen
  • Computer Science
    2010 5th International Conference on Future Information Technology
  • 2010
TLDR
Two classifiers, random forests and support vector machines are studied in application to micro array cancer data sets in hope to find out if a smaller number of good genes gives a better classification rate.
Empirical Study of Support Vector Machine Kernels with Applications to Microarray Data
TLDR
It is reported that linear kernel performance is as good as non linear kernels or slightly better in most cases and scaling data values to small numbers between 0 and 1 didn’t improve SVM performances.
METHODOLOGY FOR SELECTING MICROARRAY BIOMARKER GENES FOR CANCER CLASSIFICATION
TLDR
The results showed that the proposed methodology can identifysmall subset of relevant predictive genes and can achieve high prediction accuracy with this small subset of genes for different datasets.
Modified PSO based feature selection for Microarray data classification
TLDR
Support Vector Machines, Naïve Bayesian and k-Nearest neighbor classifiers are used for classification of publicly available biomedical microarray datasets such as Prostate cancer, Leukemia and Colon tumor and it is verified that SVM outperforms other classifiers and the performance is even improved a lot after feature selection.
A novel classification technique for cancer diagnostics based on microarray gene expression profiling (MGEP)
TLDR
A novel scheme has been developed for the classification of unknown malignant tumors into known classes using the transformation of high dimensional microarray data on to the Mahalanobis space before classification, in order to compensate for the data spreads corresponding to each class and every gene.
Microarray medical data classification using kernel ridge regression and modified cat swarm optimization based gene selection system
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 35 REFERENCES
Comparison of Discrimination Methods for the Classification of Tumors Using Gene Expression Data
TLDR
Different discrimination methods for the classification of tumors based on gene expression data include nearest-neighbor classifiers, linear discriminant analysis, and classification trees, which are applied to datasets from three recently published cancer gene expression studies.
Diagnosis of multiple cancer types by shrunken centroids of gene expression
TLDR
The method of “nearest shrunken centroids” identifies subsets of genes that best characterize each class, which was highly efficient in finding genes for classifying small round blue cell tumors and leukemias.
Graphical Methods for Class Prediction Using Dimension Reduction Techniques on DNA Microarray Data
TLDR
Simple graphical classification and prediction tools for tumor status using gene-expression profiles based on two dimension estimation techniques sliced average variance estimation (SAVE) and sliced inverse regression (SIR).
Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks
TLDR
The ability of the trained ANN models to recognize SRBCTs is demonstrated, and the potential applications of these methods for tumor diagnosis and the identification of candidate targets for therapy are demonstrated.
Evolutionary algorithms for finding optimal gene sets in microarray prediction
TLDR
A replication algorithm is used to evolve an ensemble of predictors, all using different combinations of genes to generate a set of optimal predictors that could be used clinically by making antibody assays to diagnose a specific type of cancer.
Class Prediction by Nearest Shrunken Centroids, with Applications to DNA Microarrays
We propose a new method for class prediction in DNA microarray studies based on an enhancement of the nearest prototype classifier. Our technique uses "shrunken" centroids as prototypes for each…
Molecular classification of cancer: class discovery and class prediction by gene expression monitoring.
TLDR
A generic approach to cancer classification based on gene expression monitoring by DNA microarrays is described and applied to human acute leukemias as a test case and suggests a general strategy for discovering and predicting cancer classes for other types of cancer, independent of previous biological knowledge.
Missing value estimation methods for DNA microarrays
TLDR
It is shown that KNNimpute appears to provide a more robust and sensitive method for missing value estimation than SVDimpute, and both SVD Impute and KNN Impute surpass the commonly used row average method (as well as filling missing values with zeros).
Significance analysis of microarrays applied to the ionizing radiation response
TLDR
A method that assigns a score to each gene on the basis of change in gene expression relative to the standard deviation of repeated measurements is described, suggesting that this repair pathway for UV-damaged DNA might play a previously unrecognized role in repairing DNA damaged by ionizing radiation.
Gene expression patterns in human liver cancers.
TLDR
Using cDNA microarrays to characterize patterns of gene expression in Hepatocellular carcinoma, consistent differences between the expression patterns in HCC compared with those seen in nontumor liver tissues are found.
...
1
2
3
4
...